Claude Sonnet 5.5 vs Muse Ember
TryTop 2 now
Claude Sonnet 5.5 leads by 4.4 capability points (≈95% interval +1.9 to +6.9): a clear lead over Muse Ember · P(higher) ≈ 100%
Wins 47 of 50 shared benchmarks (3 lost)
Capability vs. relative cost
Claude Sonnet 5.5Muse EmberClosed weightsOpen weights
Benchmark wins47 – 3 · 50 shared
Comparing matching setups only (3 benchmarks excluded) · suites counted once
Area← Claude Sonnet 5.5Muse Ember →
Data: Artificial Analysis, Surge AI, Arena and 11 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Muse Ember minus Claude Sonnet 5.5.
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 53.3 | 20.0 | −33.3 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 15.6 | 1.0 | −28.5 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 53.3 | 25.1 | −28.2 |
| DAXBench v2 | Software › Data & ML | 86.2 | 62.8 | −23.4 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 41.7 | 18.3 | −23.3 |
| RiemannBench (November 2026 rescoring) | Math | 76.8 | 53.6 | −23.2 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 63.6 | 40.9 | −22.7 |
| LMArena Code Arena WebDev | Software › Frontend & design | 1773 | 1608 | −21.9 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 54.5 | 36.0 | −18.5 |
| DeepFinance | Professional › Finance, accounting & tax | 54.6 | 36.5 | −18.1 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 47.7 | 29.8 | −17.9 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 34.0 | 17.2 | −16.8 |
| Artificial Analysis Engineering Index | Science › Engineering | 58.5 | 41.8 | −16.7 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 30.7 | -2.7 | −16.7 |
| APEX-1 (Mercor, mean score) | Professional › General knowledge work | 53.9 | 70.4 | +16.5 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 40.5 | 24.2 | −16.3 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1815 | 1520 | −16.2 |
| TaxCalcBench TY25 | Professional › Finance, accounting & tax | 18.0 | 2.0 | −16.0 |
| HLAB-Vals-1.1 | Professional › Legal | 10.4 | 25.0 | +14.6 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 41.7 | 27.2 | −14.5 |
| Artificial Analysis Legal Index | Professional › Legal | 52.2 | 38.5 | −13.7 |
| GDP.xlsx | Professional › General knowledge work | 29.1 | 15.4 | −13.7 |
| APEX-SWE | Software › Software engineering | 66.4 | 52.9 | −13.5 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 75.7 | 62.3 | −13.4 |
| Artificial Analysis Economics Index | Composite indexes | 54.1 | 41.0 | −13.1 |
| Artificial Analysis Healthcare & Medical Index | Health & medicine | 54.2 | 41.3 | −12.9 |
| SWE Atlas v1.1 - Overall | Software › Software engineering | 68.3 | 56.0 | −12.3 |
| Ramp SWE-Bench v2 | Software › Software engineering | 63.2 | 51.8 | −11.4 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 30.5 | 7.7 | −11.4 |
| BuseyBench SVG | Perception & media › Generation | 6.5 | 5.4 | −11.3 |
| Artificial Analysis Finance & Accounting Index | Professional › Finance, accounting & tax | 55.8 | 44.6 | −11.2 |
| GBENCH One-shot Coding GScore | Games | 66.4 | 56.4 | −10.0 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 17.6 | -2.0 | −9.8 |
| Artificial Analysis Strategy & Ops Index | Professional › General knowledge work | 58.1 | 48.7 | −9.4 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 70.8 | 62.1 | −8.7 |
| Vibe Code Bench v1.1 | Software › Frontend & design | 92.4 | 83.7 | −8.7 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 67.2 | 58.8 | −8.4 |
| KradleBench | Games | 33.8 | 25.7 | −8.1 |
| APEX-Agents 1.1 | Professional › General knowledge work | 83.7 | 75.7 | −8.0 |
| Artificial Analysis Progress Index v1 | Composite indexes | 351 | 329 | −7.6 |
| FORTRESS Average Risk Score (ARS) | Safety & alignment | 18.2 | 11.9 | +6.3 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 14.8 | 4.8 | −5.0 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 75.9 | 72.2 | −3.7 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 71.8 | 68.1 | −3.7 |
| SimpleBench | Knowledge & reasoning › General knowledge | 75.9 | 72.7 | −3.2 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 25.8 | 22.8 | −3.0 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | 11.9 | 6.6 | −2.6 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 51.2 | 49.2 | −2.0 |
| τ³-Banking (Mercor run, bm25_grep retrieval) | Tool & computer use › Customer service & operations | 54.0 | 53.3 | −0.7 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 1.0 | 0.9 | 0.0 |
Data: Artificial Analysis, Surge AI, Arena and 11 othersatlas.village.dev